Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to different types of firearm models

    oai_token-act-pair · gpt-3.5-turbo

    references to semi-automatic weapons and firearms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rica
    -0.89
     Zup
    -0.73
     Blaz
    -0.72
     Larson
    -0.72
     Brooks
    -0.71
     Scrib
    -0.70
     Fen
    -0.70
    atche
    -0.69
     Watson
    -0.69
     Zimmer
    -0.68
    POSITIVE LOGITS
    iron
    0.98
    finals
    0.98
    conscious
    0.97
    interstitial
    0.96
    skilled
    0.95
    exclusive
    0.94
    functional
    0.91
    conduct
    0.91
    det
    0.90
    automatic
    0.90
    Act Density 0.040%

    No Known Activations